feat(cli): implement 'lore trace' command (bd-2n4, bd-9dd)

Gate 5 Code Trace - Tier 1 (API-only, no git blame).
Answers 'Why was this code introduced?' by building
file -> MR -> issue -> discussion chains.

New files:
- src/core/trace.rs: run_trace() query logic with rename-aware
  path resolution, entity_reference-based issue linking, and
  DiffNote discussion extraction
- src/core/trace_tests.rs: 7 unit tests for query logic
- src/cli/commands/trace.rs: CLI command with human output,
  robot JSON output, and :line suffix parsing (5 tests)

Human output shows full content (no truncation).
Robot JSON truncates discussion bodies to 500 chars for token efficiency.

Wiring:
- TraceArgs + Commands::Trace in cli/mod.rs
- handle_trace in main.rs
- VALID_COMMANDS + robot-docs manifest entry
- COMMAND_FLAGS autocorrect registry entry

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
teernisse
2026-02-17 14:16:45 -05:00
parent a1bca10408
commit 171260a772
13 changed files with 1807 additions and 283 deletions

262
src/core/trace.rs Normal file
View File

@@ -0,0 +1,262 @@
use serde::Serialize;
use super::error::Result;
use super::file_history::resolve_rename_chain;
use super::time::ms_to_iso;
/// Maximum rename chain BFS depth.
const MAX_RENAME_HOPS: usize = 10;
/// A linked issue found via entity_references on the MR.
#[derive(Debug, Serialize)]
pub struct TraceIssue {
pub iid: i64,
pub title: String,
pub state: String,
pub reference_type: String,
pub web_url: Option<String>,
}
/// A DiffNote discussion relevant to the traced file.
#[derive(Debug, Serialize)]
pub struct TraceDiscussion {
pub discussion_id: String,
pub mr_iid: i64,
pub author_username: String,
pub body: String,
pub path: String,
pub created_at_iso: String,
}
/// A single trace chain: an MR that touched the file, plus linked issues and discussions.
#[derive(Debug, Serialize)]
pub struct TraceChain {
pub mr_iid: i64,
pub mr_title: String,
pub mr_state: String,
pub mr_author: String,
pub change_type: String,
pub merged_at_iso: Option<String>,
pub updated_at_iso: String,
pub web_url: Option<String>,
pub issues: Vec<TraceIssue>,
pub discussions: Vec<TraceDiscussion>,
}
/// Result of a trace query.
#[derive(Debug, Serialize)]
pub struct TraceResult {
pub path: String,
pub resolved_paths: Vec<String>,
pub renames_followed: bool,
pub trace_chains: Vec<TraceChain>,
pub total_chains: usize,
}
/// Run the trace query: file -> MR -> issue chain.
pub fn run_trace(
conn: &rusqlite::Connection,
project_id: Option<i64>,
path: &str,
follow_renames: bool,
include_discussions: bool,
limit: usize,
) -> Result<TraceResult> {
// Resolve rename chain
let (all_paths, renames_followed) = if follow_renames {
if let Some(pid) = project_id {
let chain = resolve_rename_chain(conn, pid, path, MAX_RENAME_HOPS)?;
let followed = chain.len() > 1;
(chain, followed)
} else {
(vec![path.to_string()], false)
}
} else {
(vec![path.to_string()], false)
};
// Build placeholders for IN clause
let placeholders: Vec<String> = (0..all_paths.len())
.map(|i| format!("?{}", i + 2))
.collect();
let in_clause = placeholders.join(", ");
let project_filter = if project_id.is_some() {
"AND mfc.project_id = ?1"
} else {
""
};
// Step 1: Find MRs that touched the file
let mr_sql = format!(
"SELECT DISTINCT \
mr.id, mr.iid, mr.title, mr.state, mr.author_username, \
mfc.change_type, mr.merged_at, mr.updated_at, mr.web_url \
FROM mr_file_changes mfc \
JOIN merge_requests mr ON mr.id = mfc.merge_request_id \
WHERE mfc.new_path IN ({in_clause}) {project_filter} \
ORDER BY COALESCE(mr.merged_at, mr.updated_at) DESC \
LIMIT ?{}",
all_paths.len() + 2
);
let mut stmt = conn.prepare(&mr_sql)?;
let mut params: Vec<Box<dyn rusqlite::types::ToSql>> = Vec::new();
params.push(Box::new(project_id.unwrap_or(0)));
for p in &all_paths {
params.push(Box::new(p.clone()));
}
params.push(Box::new(limit as i64));
let param_refs: Vec<&dyn rusqlite::types::ToSql> = params.iter().map(|p| p.as_ref()).collect();
struct MrRow {
id: i64,
iid: i64,
title: String,
state: String,
author: String,
change_type: String,
merged_at: Option<i64>,
updated_at: i64,
web_url: Option<String>,
}
let mr_rows: Vec<MrRow> = stmt
.query_map(param_refs.as_slice(), |row| {
Ok(MrRow {
id: row.get(0)?,
iid: row.get(1)?,
title: row.get(2)?,
state: row.get(3)?,
author: row.get(4)?,
change_type: row.get(5)?,
merged_at: row.get(6)?,
updated_at: row.get(7)?,
web_url: row.get(8)?,
})
})?
.filter_map(std::result::Result::ok)
.collect();
// Step 2: For each MR, find linked issues + optional discussions
let mut trace_chains = Vec::with_capacity(mr_rows.len());
for mr in &mr_rows {
let issues = fetch_linked_issues(conn, mr.id)?;
let discussions = if include_discussions {
fetch_trace_discussions(conn, mr.id, mr.iid, &all_paths)?
} else {
Vec::new()
};
trace_chains.push(TraceChain {
mr_iid: mr.iid,
mr_title: mr.title.clone(),
mr_state: mr.state.clone(),
mr_author: mr.author.clone(),
change_type: mr.change_type.clone(),
merged_at_iso: mr.merged_at.map(ms_to_iso),
updated_at_iso: ms_to_iso(mr.updated_at),
web_url: mr.web_url.clone(),
issues,
discussions,
});
}
let total_chains = trace_chains.len();
Ok(TraceResult {
path: path.to_string(),
resolved_paths: all_paths,
renames_followed,
trace_chains,
total_chains,
})
}
/// Fetch issues linked to an MR via entity_references.
/// source = merge_request -> target = issue (closes/mentioned/related)
fn fetch_linked_issues(conn: &rusqlite::Connection, mr_id: i64) -> Result<Vec<TraceIssue>> {
let sql = "SELECT DISTINCT i.iid, i.title, i.state, er.reference_type, i.web_url \
FROM entity_references er \
JOIN issues i ON i.id = er.target_entity_id \
WHERE er.source_entity_type = 'merge_request' \
AND er.source_entity_id = ?1 \
AND er.target_entity_type = 'issue' \
AND er.target_entity_id IS NOT NULL \
ORDER BY \
CASE er.reference_type WHEN 'closes' THEN 0 WHEN 'related' THEN 1 ELSE 2 END, \
i.iid";
let mut stmt = conn.prepare(sql)?;
let issues: Vec<TraceIssue> = stmt
.query_map(rusqlite::params![mr_id], |row| {
Ok(TraceIssue {
iid: row.get(0)?,
title: row.get(1)?,
state: row.get(2)?,
reference_type: row.get(3)?,
web_url: row.get(4)?,
})
})?
.filter_map(std::result::Result::ok)
.collect();
Ok(issues)
}
/// Fetch DiffNote discussions on a specific MR that reference the traced paths.
fn fetch_trace_discussions(
conn: &rusqlite::Connection,
mr_id: i64,
mr_iid: i64,
paths: &[String],
) -> Result<Vec<TraceDiscussion>> {
let placeholders: Vec<String> = (0..paths.len()).map(|i| format!("?{}", i + 2)).collect();
let in_clause = placeholders.join(", ");
let sql = format!(
"SELECT d.gitlab_discussion_id, n.author_username, n.body, n.position_new_path, n.created_at \
FROM notes n \
JOIN discussions d ON d.id = n.discussion_id \
WHERE d.merge_request_id = ?1 \
AND n.position_new_path IN ({in_clause}) \
AND n.is_system = 0 \
ORDER BY n.created_at DESC \
LIMIT 20"
);
let mut stmt = conn.prepare(&sql)?;
let mut params: Vec<Box<dyn rusqlite::types::ToSql>> = Vec::new();
params.push(Box::new(mr_id));
for p in paths {
params.push(Box::new(p.clone()));
}
let param_refs: Vec<&dyn rusqlite::types::ToSql> = params.iter().map(|p| p.as_ref()).collect();
let discussions: Vec<TraceDiscussion> = stmt
.query_map(param_refs.as_slice(), |row| {
let created_at: i64 = row.get(4)?;
Ok(TraceDiscussion {
discussion_id: row.get(0)?,
mr_iid,
author_username: row.get(1)?,
body: row.get(2)?,
path: row.get(3)?,
created_at_iso: ms_to_iso(created_at),
})
})?
.filter_map(std::result::Result::ok)
.collect();
Ok(discussions)
}
#[cfg(test)]
#[path = "trace_tests.rs"]
mod tests;